Agent Engineering

Observability: What Is the Agent Doing and How Much Is It Costing?

Event stream + stats panel · Monitor the full Agent lifecycle in real time. Click "Simulate a Task" to see the complete event stream for a real task.

Live Monitor Dashboard
Ready · Click the button to start the simulation
Event Stream
Waiting for task to start…
⏱️
Total Time
s
🧠
LLM Calls
0×
🔧
Tool Calls
0×
📥
Input Tokens
0
📤
Output Tokens
0
💰
Est. Cost
¥0.00
📁
File Changes
0files
Design Decisions
📌 Design Decision 1
No observability = black box. When users ask "Why is the Agent so slow?" or "Why did this cost so much?", you need data to answer.
📌 Design Decision 2
Every event type is a product decision point: text for streaming display, tool_start/end for progress bars, usage for billing, error for alerts.
📌 Design Decision 3
Alice uses the OpenTelemetry standard to record all spans: agent.turn, llm.request, tool.execution, context.compress. This lets you analyze performance with any APM tool.
Takeaway The Agent is not a black box: through the event stream, you can see in real time what it is thinking, doing, and spending. Observability is the infrastructure for product operations — without it, you cannot optimize costs, debug failures, or improve user experience.